Adversarial attacks on machine learning cybersecurity defences in Industrial Control Systems. (May 2021)

• Record Type: Journal Article
• Authors: Anthi, Eirini; Williams, Lowri; Rhode, Matilda; Burnap, Pete; Wedgbury, Adam
• Is Part Of: Journal of information security and applications. Volume 58(2021)
• Publication Date: 2021-05
• Subjects: Industrial Control Systems -- Supervised machine learning -- Adversarial Machine Learning -- Attack detection -- Intrusion Detection System; Computer security -- Periodicals; Information technology -- Security measures -- Periodicals; 005.805
• DOI: 10.1016/j.jisa.2020.102717
• Languages: English
• ISSNs: 2214-2126

Abstract

Abstract: The proliferation and application of machine learning-based Intrusion Detection Systems (IDS) have allowed for more flexibility and efficiency in the automated detection of cyber attacks in Industrial Control Systems (ICS). However, the introduction of such IDSs has also created an additional attack vector; the learning models may also be subject to cyber attacks, otherwise referred to as Adversarial Machine Learning (AML). Such attacks may have severe consequences in ICS systems, as adversaries could potentially bypass the IDS. This could lead to delayed attack detection which may result in infrastructure damages, financial loss, and even loss of life. This paper explores how adversarial learning can be used to target supervised models by generating adversarial samples using the Jacobian-based Saliency Map attack and exploring classification behaviours. The analysis also includes the exploration of how such samples can support the robustness of supervised models using adversarial training. An authentic power system dataset was used to support the experiments presented herein. Overall, the classification performance of two widely used classifiers, Random Forest and J48, decreased by 6 and 11 percentage points when adversarial samples were present. Their performances improved following adversarial training, demonstrating their robustness towards such attacks.